From owner-freebsd-arch@FreeBSD.ORG  Fri Oct  7 09:29:02 2005
Return-Path: <owner-freebsd-arch@FreeBSD.ORG>
X-Original-To: arch@FreeBSD.org
Delivered-To: freebsd-arch@FreeBSD.ORG
Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125])
	by hub.freebsd.org (Postfix) with ESMTP id 38F2016A420;
	Fri,  7 Oct 2005 09:29:02 +0000 (GMT) (envelope-from _pppp@mail.ru)
Received: from f44.mail.ru (f44.mail.ru [194.67.57.82])
	by mx1.FreeBSD.org (Postfix) with ESMTP id 2294343D66;
	Fri,  7 Oct 2005 09:28:59 +0000 (GMT) (envelope-from _pppp@mail.ru)
Received: from mail by f44.mail.ru with local 
	id 1ENoXC-000CxD-00; Fri, 07 Oct 2005 13:28:58 +0400
Received: from [212.5.170.174] by win.mail.ru with HTTP;
	Fri, 07 Oct 2005 13:28:58 +0400
From: dima <_pppp@mail.ru>
To: Gleb Smirnoff <glebius@FreeBSD.org>
Mime-Version: 1.0
X-Mailer: mPOP Web-Mail 2.19
X-Originating-IP: [212.5.170.174]
Date: Fri, 07 Oct 2005 13:28:58 +0400
In-Reply-To: <20051006183413.GH14542@cell.sick.ru>
Content-Type: text/plain; charset=koi8-r
Content-Transfer-Encoding: 8bit
Message-Id: <E1ENoXC-000CxD-00._pppp-mail-ru@f44.mail.ru>
Cc: arch@FreeBSD.org
Subject: Re[2]: [REVIEW/TEST] polling(4) changes
X-BeenThere: freebsd-arch@freebsd.org
X-Mailman-Version: 2.1.5
Precedence: list
Reply-To: dima <_pppp@mail.ru>
List-Id: Discussion related to FreeBSD architecture <freebsd-arch.freebsd.org>
List-Unsubscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-arch>,
	<mailto:freebsd-arch-request@freebsd.org?subject=unsubscribe>
List-Archive: <http://lists.freebsd.org/pipermail/freebsd-arch>
List-Post: <mailto:freebsd-arch@freebsd.org>
List-Help: <mailto:freebsd-arch-request@freebsd.org?subject=help>
List-Subscribe: <http://lists.freebsd.org/mailman/listinfo/freebsd-arch>,
	<mailto:freebsd-arch-request@freebsd.org?subject=subscribe>
X-List-Received-Date: Fri, 07 Oct 2005 09:29:02 -0000

> d> Seems to be a first considerable step regarding the ideas discussed in March :)
> d> But, my idea about the separate locking of each interface dissappeared from this implementation. mtx_poll is good to protect the pollrec array and other sensitive variables. But we could get advantage of SMP machines writing polling loops like this:
> d> 
> d> for( i = 0; i < poll_handlers; ++i ) {
> d>   mtx_lock( &iface_lock[i] );
> d>   pr[i].handler(pr[i].ifp, POLL_ONLY, count);
> d>   mtx_unlock( &iface_lock[i] );
> d> }
> 
> What is the benefit here? The driver must have its own lock.

Well, consider the absense of the mtx_poll lock:

- mtx_lock( &mtx_poll );
  for( i = 0; i < poll_handlers; ++i ) {
+   mtx_lock( &iface_lock[i] );
    pr[i].handler( pr[i].ifp, POLL_ONLY, count );
+   mtx_unlock( &iface_lock[i] );
  }
- mtx_unlock( &mtx_poll );

So, several kernel threads in an SMP machine can poll different interfaces simultaneously. And mtx_lock should only be used in ether_poll_[de]register().